A brief overview of the issues faced by Harmful Algal Blooms along Johor straits

Urbanization of coastal areas worldwide has increased due to an increase in the global population. The production of sustainable aquaculture is greatly impacted by a surge of this urbanization. In certain countries, particularly for individuals with more limited space in metropolitan areas, such as along Johor's coastal area, aquaculture might well be a good strategy to maintain food availability (continuous production plus high-quality meals). Consequently, the adoption of aquaculture along the Johor's coastal area has lead to Harmful Algal Blooms (HAB). This paper examines the evolution of the aquaculture industry of Malaysian Johor coastal areas in relation to HABs. In addition to HABs, the aforementioned metropolitan regions confront diverse economic and geographical obstacles when attempting to increase their aquaculture production sustainably. Those problems are therefore addressed using a variety of operations as well as surveillance techniques in this brief overview. Lockdowns and border prohibitions caused by the continuous COVID-19 infection have had a global impact. These logistical difficulties in the seafood industry have increased dependency on imported supplies. It is suggested that international decision- making, supervision, and knowledge exchange can successfully solve the challenges urbanized areas have in ensuring sustainable food security through the evolution within the aquaculture sector.

Explainable COVID-19 Three Classes Severity Classification Using Chest X-Ray Images

COVID-19 has been raging for almost three years ever since its first outbreak. It is without a doubt that it is a common human goal to end the pandemic and how it was before it started. Many efforts have been made to work toward this goal. In computer vision, works have been done to aid medical professionals into faster and more effective procedures when dealing with the disease. For example, disease diagnosis and severity prediction using chest imaging. At the same time, vision transformer is introduced and quickly stormed its way into one of the best deep learning models ever developed due to its ability to achieve good performance while being resources friendly. In this study, we investigated the performance of ViT on COVID19 severity classification using an open-source CXR images dataset. We applied different augmentation and transformation techniques to the dataset to see ViT's ability to learn the features of the different severity levels of the disease. It is concluded that training ViT using the horizontally flipped images added to the original dataset gives the best overall accuracy of 0.862. To achieve explainability, we have also applied Grad-CAM to the best performing model to make sure it is looking at relevant region of the CXR image upon predicting the class label. © 2022 IEEE.

Trauma and Coping in Battling the COVID-19 Pandemic Among Malaysian Healthcare Workers

Introduction: Prolonged COVID-19 pandemic with high morbidity and mortality may cause traumatic events to Healthcare Workers (HCW), resulting in Post-Traumatic Stress Disorder (PTSD) symptoms. Hence, this study aims to determine the prevalence of PTSD symptoms and its association with coping strategies among HCW in managing COVID-19 pandemic at Klang Valley Public Hospitals in Malaysia. Methods: A cross-sectional study with total of 424 eligible respondents were recruited through stratified random sampling. Data was collected from 6th May until 6th June 2021 using a self-administered online questionnaire adopted from MPCL-5 and Brief COPE instruments. IBM Statistical Package for Social Sciences Version 26 was used to analyse data. Result: 25% of the respondents demonstrated PTSD symptoms. Respondents who are single (aOR=3.319, 95% CI: 1.912, 5.762, p-value <0.001) and had history of positive COVID-19 (aOR= 2.563, 95% CI:1.058, 6.209, p-value=0.037) were more likely to experience PTSD symptoms. Frequently coping with self-blaming (aOR= 7.804, 95% CI: 3.467, 17.568, p-value < 0.001), behavioural disengagement (aOR= 7.262, 95% CI: 1.973, 26.723, p-value =0.003), humour (aOR= 5.303, 95% CI: 1.754, 16.039, p-value =0.003), venting emotion (aOR= 3.287, 95% CI: 1.521, 7.105, p-value =0.002) and less planning (aOR= 2.006, 95% CI:1.154, 3.487 p-value =0.014) are significant predictors for PTSD symptoms. Conclusion: One in four HCW managing COVID-19 in Klang Valley public hospitals experienced PTSD symptoms. Therefore, urgent interventional program targeting HCW who are single with history of positive COVID-19 is beneficial to prevent PTSD. Maladaptive coping strategies like self-blaming, venting emotion, humour and behavioural disengagement should be replaced with more adaptive coping strategies like planning, self-compassion, self-care and self-reflection. © 2023 Authors. All rights reserved.

IoT-Based Heart Monitoring System Implementation and Analysis

This paper presents an IoT-based heart monitoring system using 8266 NodeMCU. According to the Malaysian Department of Statistics, ischemic heart disease is the leading cause of death, accounting for 15.0% of the 109,164 medically certified deaths in 2019. The coronary heart is a vital organ that pumps oxygen and blood across the body. Meanwhile, if the heart is not getting sufficient oxygen, the patient will experience chest pain, typically on the left side of the body, which can be mistaken for a heart problem. During the Covid-19 pandemic, a patient cannot attend regular treatment at the hospital as it is operating at full capacity. During this phase, the hospital can only focus on the critical and high-risk patient. The proposed heart monitoring system monitors the patient by measuring the heart rate and oxygen level in the comforts of home. Therefore, the patient can provide his current health record for the doctor's evaluation. The idea behind this proposed system is to construct an IOT-based system that automatically monitors the health condition in terms of heartbeat and oxygen detection. The prototype provides data to the Blynk for the patient and the I-Heart web-based application for the medical practitioner. © 2022 IEEE.

WEB-BASED APPLICATION FOR ENHANCING ON-SITE AND REMOTE DATA COLLECTION PROCESS DURING PANDEMIC: AN EXPLORATORY STUDY

The COVID-19 pandemic has changed the way data collection for research takes place around the world. Such adaptation has forced a turn of research methodologies in conducting research. This study focuses on on-site and remote digital data collection methods that can be adopted during the pandemic. The method of research and data collection often requires a group of researchers to travel to a specific site to meet communities for data collection, which is not permissible during the pandemic. This paper explores the use of web-based application for documentation of the existing natural and built features, and land management system for identification of the rural community's land information. In this paper, the use of a web-based application, namely i-LULACAST, is highlighted. The application was designed and used for data entry and management of the rural community with fewer human resources on-site while still maximizing the number of datasets needed for analysis. The system was built using Codelgniter Application 4.0.4 to develop libraries to link databases and perform operations such as data entry, location, and uploading pictures for particular data. This system has also shown prospects for other purposes, such as census, landscape data entry, and contact tracing for medical purposes. © 2022 by MIP.

Lung Classification for COVID-19

The year 2020 has seen the world being traumatized with the COVID-19 pandemic. COVID-19 virus had infected more than 100 million people and 2 million deaths worldwide. Many researchers race against time in producing vaccines and also used the latest technology in data analytics and artificial intelligence to help curb the pandemic. Deep features have shown to be an emerging area of research in various fields. Most recent deep works in the lung area focused on Convolutional Neural Networks (CNN). However, these have a drawback of over-classifying and not reflective of the real-world. Therefore, this article presented a cloud-based lung disease classification system, where medical practitioners can upload their patients' chest X-ray onto the cloud, and the system will classify if the disease is absent (normal) or present (abnormal). To test the disease, the system will then classify the lung infection as COVID-19 and non-COVID. Overall, the proposed system has obtained fairly good accuracy. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Lung Classification for COVID-19

The year 2020 has seen the world being traumatized with the COVID-19 pandemic. COVID-19 virus had infected more than 100 million people and 2 million deaths worldwide. Many researchers race against time in producing vaccines and also used the latest technology in data analytics and artificial intelligence to help curb the pandemic. Deep features have shown to be an emerging area of research in various fields. Most recent deep works in the lung area focused on Convolutional Neural Networks (CNN). However, these have a drawback of over-classifying and not reflective of the real-world. Therefore, this article presented a cloud-based lung disease classification system, where medical practitioners can upload their patients' chest X-ray onto the cloud, and the system will classify if the disease is absent (normal) or present (abnormal). To test the disease, the system will then classify the lung infection as COVID-19 and non-COVID. Overall, the proposed system has obtained fairly good accuracy. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

LiWGAN: A Light Method to Improve the Performance of Generative Adversarial Network

Generative adversarial networks (GANs) gained tremendous growth due to its potential and efficacy in producing realistic samples. This study proposes a light-weight GAN (LiWGAN) to learn the non-image synthesis with minimum computational time for less power computing. Hence, the LiWGAN method enhanced a new skip-layer channel-wise excitation module (SLE) and a self-supervised discriminator design for the non-synthesis performance using the facemask dataset. The facemask is one of the preventative strategies pioneered by the current COVID-19 pandemic. LiWGAN manipulates a non-image synthesis of facemask that could be beneficial for some researchers to identify an individual using lower power devices, occlusion challenges for face recognition, and alleviate the accuracy challenges due to limited datasets. The performance compared the processing time for a facemask dataset in terms of batch sizes and image resolutions. The Fréchet inception distance (FID) was also measured on the facemask images to evaluate the quality of the augmented image using LiWGAN. The findings for 3000 generated images showed a nearly similar FID score at 220.43 with significantly less processing time per iteration at 1.03s than StyleGAN at 219.97 FID score. One experiment was conducted using the CelebA dataset to compare with GL-GAN and DRAGAN, proving LiWGAN is appropriate for other datasets. The outcomes found LiWGAN performed better than GL-GAN and DRAGAN at 91.31 FID score with 3.50s processing time per iteration. Therefore, LiWGAN could aim to enhance the FID score to be near zero in the future with less processing time by using different datasets. Author

The Role of Big Data Analytics in Digital Health for COVID-19 Prevention and Control in Asia

Big data analytics (BDA) in digital health is critical for gaining the knowledge needed to make decisions, with Asia at the forefront of utilising this technology for the Coronavirus disease 2019 (COVID-19). This review aims to study how BDA was incorporated into digital health in managing the COVID-19 pandemic in six selected Asian countries, discuss its advantages and barriers and recommend measures to improve its adoption. A narrative review was conducted. Online databases were searched to identify all relevant literature on the roles of BDA in digital health for COVID-19 preventive and control measures. The findings showed that these countries had used BDA for contact tracing, quarantine compliance, outbreak prediction, supply rationing, movement control, information update, and symptom monitoring. Compared to conventional approaches, BDA in digital health plays a more efficient role in preventing and controlling COVID-19. It may inspire other countries to adopt this technology in managing the pandemic. © 2022 UPM Press. All rights reserved.

A Densely Interconnected Convolutional Neural Network-Based Approach to Identify COVID-19 from Chest X-ray Images

The novel Corona Virus (COVID-19) has spread so rapidly that cause a devastating effect on public well-being and create an emergency around the world. Hence, the rapid identification of COVID-19 has become a challenging work within a short period. Clinical trials of patients with COVID-19 have shown that most of the patients affected by COVID-19 experience lung infection that can cause inflammation in the lung after virus-contiguity. It can damage the cells and tissue that is inside the lung. However, pneumonia is also a lung infection that can cause inflammation in the air sacs inside the lung. Chest X-rays and CT scans perform an essential role in the detection of lung-related illnesses. Therefore, concerning the diagnosis of COVID-19, radiography and chest CT are considered as fundamental imaging approaches. This study presents a densely interconnected convolutional neural network-based approach to identify COVID-19, Pneumonia and Normal patients from chest X-ray images. To experiment with the proposed methodology, a new dataset is generated by combining two different datasets from Kaggle named COVID-19 Radiography Database and Chest X-ray (COVID-19 & Pneumonia). The dataset comprises of 500 X-ray images of COVID-19 affected people, 2600 X-ray images of Normal people, and 3418 X-ray images of pneumonia affected people. The proposed densely interconnected convolutional neural network model produces 99% testing accuracy for COVID-19, 98% testing accuracy for Pneumonia and 98% testing accuracy for Normal people without the application of any augmentation techniques. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Development of Smart Healthcare Tracker through Internet of Things

According to the World Health Organization, there are approximately 17.9 million people in the world who will die under the cause of Cardiovascular diseases (CVDs) in 2019. Heart and Brain are both related to Cardiovascular diseases. Even if the patients do not pass away due to the disease, the post-effect of this illness burdens the patients and their families. Also, the outbreak of COVID-19 makes the patients take a risk of undergoing rehabilitation in the hospital. Thus, a smart healthcare solution which is a Smart Healthcare Tracker through the Internet of Things is designed. The system consists of an EMG sensor, accelerometer, gyroscope, and heart rate/pulse oximeter connected to ESP 32 with an interface of NodeMCU to study the patients' health condition for arms and legs strength by sending the data to the caregivers or physicians. The project aimed to obtain a consistent and accurate reading for each of the features for arms and legs strength analysis and sleeping disturbance analysis. The BLYNK app is also applied to the project design as a platform to display the analysis result to the caregivers/physicians on the gadgets at any time and anywhere. The prototype has been constructed and the data collection is built successfully. The prototype is trusted to obtain accurate and consistent results and can provide a sustainable way for the rehabilitation to indicate the health condition and the recovery stage of the patients. © 2021 IEEE.

Preliminary Study on Patch Sizes in Vision Transformers (ViT) for COVID-19 and Diseased Lungs Classification

COVID-19 and lung diseases have been the major focus of research currently due to the pandemic's reach and effect. Deep Learning (DL) is playing a large role today in various fields from disease classification to drug response identification. The conventional DL method used for images is the Convolutional Neural Network (CNN). A potential method that will replace the usage of CNNs is Transformer specifically Vision Transformers (ViT). This study is a preliminary exploration to determine the performance of using ViT on diseased lungs, COVID-19 infected lungs, and normal lungs. This study was performed on two datasets. The first dataset was a publicly accessible dataset from Iran that has a large cohort of patients. The second dataset was a Malaysian dataset. These images were utilized to verify the usage of ViT and its effectiveness. Images were segregated into several sized patches (16x16, 32x32, 64x64, 128x128, 256x256) pixels. To determine the performance of ViT method, performance metrics of accuracy, sensitivity, specificity, negative predictive value (NPV), positive predictive value (PPV) and F1-score. From the results of this study, ViT is a promising method with a peak accuracy of 95.36%. © 2021 IEEE.

Covid-19 Severity Classification Using Supervised Learning Approach

This paper presented work on supervised machine learning techniques using K-NN, Linear SVM, Naïve Bayes, Decision Tree (J48), Ada Boost, Bagging and Stacking for the purpose to classify the severity group of covid-19 symptoms. The data was obtained from Kaggle dataset, which was obtained through a survey collected from the participant with varying gender and age that had visited 10 or more countries including China, France, Germany Iran, Italy, Republic of Korean, Spain, UAE, other European Countries (Other-EUR) and Others. The survey is Covid-19 symptom based on guidelines given by the World Health Organization (WHO) and the Ministry of Health and Family Welfare, India which then classified into 4 different levels of severity, Mild, Moderate, Severe, and None. The results from the seven classifiers used in this study showed very low classification results. © 2021 IEEE.

A study into the development of a light weight smart life buoy prototype (LWSLB)

Life Buoy, also known as a life preserver, is a crucial safety tool on board any marine ships. The most common and conventional lifesaver is operated manually to save people from drowning, yet this method poses a risk for both the victim and rescuer. Hence, with the help of current technology, a smart lifebuoy has been developed, whereby the rescuer just operates the lifebuoy using remote control. Yet, the existing smart life buoy system has been found heavy and hard to be operated, especially for women, children, and other people with disabilities.This paper focuses on the development of a lightweight smart life buoy system and its characteristics. Arduino Uno R3, Arduino Nano, DC motor 775, Transmitter and Receiver kit were the main components used in the development of the lightweight smart life buoy system (LWSLB). The developed LWSLB system was tested at the National Defence University of Malaysia’ swimming pool due to Covid-19 lockdown, and data such as speed, range of remote connection and battery endurance were obtained. It has been found out that the developed LWSLB weighs just 3.5kg overall compared to Brand S which weighs 13.75kg. However, in terms of speed, Brand S proves to be faster at 4.17m/s compared to LWSLB which exhibits a speed of 1.25m/s. © 2021, Faculty of Maritime Studies. All rights reserved.

Analysis of web-based learning interface design based on experts’ verification for higher education

Recently, the Web-based learning (WBL) platform, particularly for higher education, has become more crucial due to the Covid-19 pandemic. Thus, due to the increased use of WBL   in higher education, an effective WBL interface design for higher education is truly important in order to attract students to use WBL and to further keep them engaged during learning via the Web-based platform. Therefore, the aim of this study was to determine the aesthetics of web interfaces based on experts’ opinions. This study adopted a quantitative research approach involving a data-gathering survey. Fifteen (15) WBL interfaces were designed based on nine (9) design principles which were balance, proportion, simplicity, alignment, movement, hierarchy, consistency, contrast, and proximity. The results of this study discovered that nine (9) WBL interfaces were determined by the experts as aesthetic interfaces, five (5) WBL interfaces as non-aesthetic and 1 (one) WBL interface was considered neither aesthetic nor non-aesthetic. This finding revealed that six (6) out of nine (9) interfaces had the balance design principle. However, balance was also in most non-aesthetic interfaces. A possible reason that balance was the most design principle in both the aesthetic and the non-aesthetic interfaces is that when designing WBL interfaces, there is a need to consider the combination of the design principles as a whole, and not count the design principles individually. In conclusion, this study's findings could contribute to the knowledge in the Human Computer Interaction domain, specifically in the interface design area. © 2021, Politeknik Negeri Padang. All rights reserved.

The next pandemic: Factors of failure in fomema tuberculosis screening amongst the foreign workers in Malaysia

The Foreign Workers’ Medical Examination Online Registration Portal or FOMEMA has been one of the key players in managing foreign workers wellbeing in Malaysia. Other than administering foreign-influenced diseased risk from entering the Malaysian land, FOMEMA’s certification for fitness to work is one of the criteria for a Visit Pass (Temporary Employment) to be issued by Immigration Department of Malaysia. However, it is difficult to control a disease that easily spread around such as Tuberculosis. Since the world is currently facing the COVID-19 pandemic, the Government needs to be aware that the mechanism of Tuberculosis infection is somehow similar. In this paper, we discussed challenges in managing Tuberculosis threat among foreign workers and what contributes to the failure in FOMEMA Tuberculosis screening. A semi-structured interview and document analysis is used as data collection techniques. The study contributes to the existing knowledge pertaining to migrant workers and tuberculosis diseases, addressing three important issues;threat of tuberculosis disease prevalence among foreign workers to the public, precautionary actions to reduce disease transmission and challenges in repatriation of migrant workers. © 2020 Ubiquity Press. All rights reserved.

Adaptive platform trials using multi-arm, multi-stage protocols: Getting fast answers in pandemic settings

Global health pandemics, such as coronavirus disease 2019 (COVID-19), require efficient and well-conducted trials to determine effective interventions, such as treatments and vaccinations. Early work focused on rapid sequencing of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), subsequent in-vitro and in-silico work, along with greater understanding of the different clinical phases of the infection, have helped identify a catalogue of potential therapeutic agents requiring assessment. In a pandemic, there is a need to quickly identify efficacious treatments, and reject those that are non-beneficial or even harmful, using randomised clinical trials. Whilst each potential treatment could be investigated across multiple, separate, competing two-arm trials, this is a very inefficient process. Despite the very large numbers of interventional trials for COVID-19, the vast majority have not used efficient trial designs. Well conducted, adaptive platform trials utilising a multi-arm multi-stage (MAMS) approach provide a solution to overcome limitations of traditional designs. The multi-arm element allows multiple different treatments to be investigated simultaneously against a shared, standard-of-care control arm. The multi-stage element uses interim analyses to assess accumulating data from the trial and ensure that only treatments showing promise continue to recruitment during the next stage of the trial. The ability to test many treatments at once and drop insufficiently active interventions significantly speeds up the rate at which answers can be achieved. This article provides an overview of the benefits of MAMS designs and successes of trials, which have used this approach to COVID-19. We also discuss international collaboration between trial teams, including prospective agreement to synthesise trial results, and identify the most effective interventions. We believe that international collaboration will help provide faster answers for patients, clinicians, and health care systems around the world, including for future waves of COVID-19, and enable preparedness for future global health pandemics.